OFA-Sys
Unlocking the power of multimodal general AI. See more recent works of our group at https://github.com/QwenLM
China
Pinned Repositories
Chinese-CLIP
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
DAFlow
Ditto
A self-ailgnment method for role-play. Benchmark for role-play. Resources for "Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment".
ExpertLLaMA
An opensource ChatBot built with ExpertPrompting which achieves 96% of ChatGPT's capability.
gsm8k-ScRel
Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
InsTag
InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning
OFA
Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
OFASys
OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models
ONE-PEACE
A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
TouchStone
Touchstone: Evaluating Vision-Language Models by Language Models
OFA-Sys's Repositories
OFA-Sys/Chinese-CLIP
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
OFA-Sys/OFA
Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
OFA-Sys/ONE-PEACE
A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
OFA-Sys/ExpertLLaMA
An opensource ChatBot built with ExpertPrompting which achieves 96% of ChatGPT's capability.
OFA-Sys/gsm8k-ScRel
Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
OFA-Sys/InsTag
InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning
OFA-Sys/Ditto
A self-ailgnment method for role-play. Benchmark for role-play. Resources for "Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment".
OFA-Sys/OFASys
OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models
OFA-Sys/DAFlow
OFA-Sys/TouchStone
Touchstone: Evaluating Vision-Language Models by Language Models
OFA-Sys/DiverseEvol
Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning
OFA-Sys/AIR-Bench
AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension
OFA-Sys/diffusion-deploy
OFA-Sys/OFA-Compress
OFA-Compress is a unified framework which provides OFA model finetuning, distillation and inference capabilities in Huggingface version, and is committed to promoting the lightweighting of large models.
OFA-Sys/MoFusion
Pretrained Diffusion Models for Unified Human Motion Synthesis
OFA-Sys/Demo_CTTS
present speech demo of FTTS